发表机构
Northwestern Polytechnical University; School of Astronautics; Research Center for Intelligent Robotics; National Key Laboratory of Aerospace Flight Dynamics（西北工业大学; 航天学院; 智能机器人研究中心; 航空航天飞行动力学重点实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文针对自动驾驶系统难以匹配用户个性化驾驶风格的问题，提出STAGE风格可控动作生成方法，通过模仿学习与偏好学习实现风格控制，实验验证其风格对齐与安全性能。
AI 中文摘要
驾驶风格是驾驶员在驾驶过程中保持的行为偏好，由其不同的经历、习惯和需求塑造，通常表现为不同程度的激进性。如果人类选择使用自动驾驶系统，会期望系统的驾驶风格与自身习惯高度相似，但当前工业级自动驾驶系统难以满足这一需求。为解决该问题，本文开发了面向驾驶任务的风格可控动作生成方法STAGE。其训练过程基于模仿学习，融合风格值与潜在值动作模态编码；随后采用偏好学习将用户驾驶风格识别为连续、单调的风格值，为降低偏好训练过程中的人力成本，还开发了一套规则用于对比数据对中的驾驶风格。推理阶段，用户输入风格值即可控制生成的动作模式，动态满足自身期望。通过STAGE方法验证，在多种典型道路场景中，风格可控的动作生成结果与人类期望高度一致；此外，将STAGE方法与多种其他方法对比，揭示了STAGE的独特功能，包括风格可控性、风格连续性、驾驶风格对齐能力及驾驶安全性。本工作的代码可在指定URL获取。
英文摘要
Driving style refers to the behavioral preferences that drivers maintain during driving, shaped by their diverse experiences, habits, and needs, and is typically reflected in varying levels of aggressiveness. If humans choose to use autonomous driving systems, they would expect the driving style of the systems to closely resemble their own habit. However, this is challenging for current industrial autonomous driving systems. To address this, we developed a style controllable action generation method, STAGE, for driving tasks. Its training process is based on imitation learning, incorporating both style value and latent value action modality encoding. Preference learning is then used to identify the user's driving style as a continuous, monotonic style value. And to reduce the cost of human involvement in the preference training process, we also developed a set of rules to compare driving style in data pairs. Then, during inference, the user inputs the style value to control the generated action patterns, dynamically meeting the user's expectations. Using the STAGE method, we verified that the style-controlled action generation results in several typical road scenarios significantly align with human expectations. Furthermore, through comparisons between the STAGE method and various other approaches, we reveal the unique functionalities of STAGE, including its style controllability, style continuity, driving style alignment capability and driving safety. The code for this work is available at: https://github.com/CarlDegio/STAGE
CommentsAccepted for publication in IEEE Robotics and Automation Letters
Journal refIEEE Robotics and Automation Letters, vol. 11, no. 2, pp. 2130-2137, Feb. 2026
